研究方向
统计模拟、辐射传输模拟、激光雷达遥感.
基本介绍
从事激光雷达遥感算法、一类分类算法/物种分布模型、三维辐射传输模型的开发和应用研究。已发表中英文论文50多篇，Google Scholar引用4608次。担任《遥感学报》第六届青年编委、国际数字地球学会中国国家委员会数字生态专业委员会委员和Frontiers in Earth Science-Geoinformatics副主编。代表成果包括：
(1) 提出基于一类数据的建模方法PBL (presence and background learning)和PBLC (positive and background learning with constraints)；提出基于一类数据的模型评价指标Fpb/Fcpb和评价曲线PB-ROC/PR plots。适用于解决单类分类/二值分类中缺乏标记负样本的问题(如物种分布模拟、遥感影像单类识别等)。
(2) 提出基于激光雷达点云的单木分割算法，为开源软件R的激光雷达数据处理包lidR和商业软件LiDAR360采用，Google Scholar引用970次，获得2013年美国摄影测量与遥感协会(ASPRS)的Talbert Abrams Award。
(3) 提出基于激光雷达点云数据和高性能计算的三维辐射传输模型VBRT (voxel-based radiative transfer)，可模拟太阳辐射传输、遥感成像等过程。
学术网页
ResearchGate
https://www.researchgate.net/profile/Wenkai-Li-13
Google Scholor
https://scholar.google.com/citations?hl=en&user=s_TDQzIAAAAJ
Web of Science
https://webofscience.clarivate.cn/wos/author/record/AFM-7916-2022
教育背景
2008-2013：加州大学默塞德分校环境系统专业，博士
2005-2008：北京大学环境工程专业，硕士
2001-2005：中山大学环境科学专业，学士
工作经历
2014-现在：中山大学地理科学与规划学院，副教授
2013-2014：加州大学默塞德分校内华达研究所，助理研究员
代表论文(*通信作者)
21. Li, W.*, Liu, H., Hu, X., Lu, X., Tao, S., Ma, Q., Yang, H., Liu, Y., Li, M., Li, T., and Guo, Q., 2026. Mapping the global potential of onshore field-scale solar PV using positive-unlabeled deep learning. Applied Energy, 402: 127025.
20. Li, W.*, Liu, H., and Li, M., 2026. Mapping the global development likelihood of wastewater treatment plants using a novel positive-unlabeled deep neural network. Journal of Cleaner Production, 558: 148265.
19. Liu, H., Liu, Y., Li, M., Liang, C., and Li, W.*, 2026. Enhancing Forest Biomass Estimation with Synthetic Airborne Laser Scanning via Voxel-based Forest Reconstruction. Journal of Plant Ecology, rtag051, https://doi.org/10.1093/jpe/rtag051.
18. Li, W.*, Hu, X., Su, Y., Tao, S., Ma, Q., and Guo, Q., 2024. A new method for voxel-based modelling of three-dimensional forest scenes with integration of terrestrial and airborne LiDAR data. Methods in Ecology and Evolution, 15: 569–582. (Top cited article in Methods in Ecology and Evolution)
17. Li, W.*, Liu, Y., Liu, Z., Gao, Z., Huang, H., and Huang, W. 2022. A positive-unlabeled learning algorithm for urban flood susceptibility modeling. Land, 11(11): 1971.
16. Li, W.*, and Guo, Q., 2021. Plotting receiver operating characteristic and precision-recall curves from presence and background data. Ecology and Evolution, 11(15): 10192–10206.
15. Li, W.*, Guo, Q., and Elkan, C., 2021. One-class remote sensing classification from positive and unlabeled background data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14: 730–746.
14. Deng, X., Li, W.*, Liu, X., Guo, Q., and Newsam, S., 2018. One-class remote sensing classification: one-class vs. binary classifiers. International Journal of Remote Sensing, 39(6): 1890–1910.
13. Liu, R., Li, W.*, Liu, X., Lu, X., Li, T., and Guo, Q., 2018. An ensemble of classifiers based on positive and unlabeled data in one-class remote sensing classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,11(2): 572–584.
12. Li, W.*, Guo, Q., Tao, S., and Su, Y., 2018. VBRT: a novel voxel-based radiative transfer model for heterogeneous three-dimensional forest scenes. Remote Sensing of Environment, 206: 318–335.
11. Li, W., and Guo, Q., 2014. A new accuracy assessment method for one-class remote sensing classification. IEEE Transactions on Geoscience and Remote Sensing, 52(8): 4621–4632.
10. Li, W., and Guo, Q., 2013. How to assess the prediction accuracy of species presence–absence models without absence data?. Ecography, 36(7): 788–799.
09. Li, W., Guo, Q., Jakubowski M.K, and Kelly, M., 2012. A new method for segmenting individual trees from the lidar point cloud. Photogrammetric Engineering & Remote Sensing, 78(1): 75–84. (Talbert Abrams Award)
08. Li, W., Guo, Q., and Elkan, C., 2011. Can we model the probability of presence of species without absence data?. Ecography, 34(6): 1096–1105.
07. Li, W., Guo, Q., and Elkan, C., 2011. A positive and unlabeled learning algorithm for one-class classification of remote sensing data. IEEE Transactions on Geoscience and Remote Sensing, 49(2): 717–725.
06. Li, W., and Guo, Q., 2010. A maximum entropy approach to one-class classification of remote sensing imagery. International Journal of Remote Sensing, 31(8): 2227–2235.
05. 刘原池, 李文楷*, 刘红良, 李明轩, 2025. 基于旋转薄片体素化森林三维重构方法. 中山大学学报(自然科学版)(中英文), 64(5): 84–99.
04. 黄伟钧, 李佳豪, 刘子越, 胡晓梅, 黄华兵, 李文楷*, 2023. 基于PBLC算法的滑坡空间易发性分析. 中山大学学报(自然科学版)(中英文), 62(4): 54–64.
03. 胡晓梅, 李文楷*, 李佳豪, 刘子越, 黄伟钧, 2022. 耦合像素坐标的遥感图像分类实验. 地理与地理信息科学, 38(5): 24–30.
02. 刘冉, 李文楷*, 刘小平, 陈逸敏, 刘珍环, 2018. 基于PUL算法及高分辨率WorldView影像的城市不透水面提取. 地理与地理信息科学, 34(1): 40–46.
01. 周中一, 刘冉, 时书纳, 苏艳军, 李文楷*, 郭庆华, 2018. 基于激光雷达数据的物种分布模拟-以美国加州内华达山脉南部区域食鱼貂分布模拟为例. 生物多样, 26(8): 878–891.
学术报告
5. “基于机载与地基激光雷达数据的森林三维建模”, 第十期激光雷达森林生态应用培训班, 北京大学, 6/28/2025.
4. “Modeling of 3D Forests Using Lidar Data”, Theory and Methods of Land Surface Remote Sensing Inversion Summer School, 北京师范大学, 7/11/2022.
3. “地理空间分布模拟中的一类数据问题”, 第一届生态遥感新方法研讨班, 中国科学院植物研究所, 12/2/2022.
2. “基于激光雷达数据 (Lidar) 森林三维辐射传输模拟”, 第五期激光雷达森林生态应用培训班, 中国科学院植物研究所, 6/3/2019.
1. “A New Accuracy Measure for One-Class Classification of Remote Sensing Data”, Association of American Geographers 2013 Annual Meeting, Los Angeles, CA, 4/9/2013. (2nd winner for Remote Sensing Specialty Group Student Honors Paper Competition)
专利软著
08. 李文楷, 黄伟钧, 胡晓梅, 刘子越, 李佳豪, 2025. 一种森林场景体素模型构建方法及系统. ZL 2022 1 0775299.2.
07. 李文楷, 胡晓梅, 刘子越, 李佳豪, 黄伟钧, 2025. 一种遥感影像不透水面提取方法及系统. ZL 2022 1 0625199.1.
06. 李文楷, 2021. 基于Lidar数据的植被冠层辐射传输模拟方法. ZL 2017 1 1478381.4.
05. 刘红良, 李文楷, 2026. 森林点云单木分割算法评估与可视化系统. 软著登字第17457467号.
04 黄伟钧, 李文楷, 刘子越, 刘原池, 刘红良, 2024. 基于LSTM模型的森林火灾风险评估系统. 软著登字第12416998号.
03. 刘子越, 李文楷, 黄伟钧, 刘原池, 刘红良, 2023. 基于有约束正样本-背景学习(PBLC)的物种分布模拟系统. 软著登字第12205856号.
02. 李文楷, 胡晓梅, 2021. 基于有约束正样本-背景学习(PBLC)的分类模型系统. 软著登字第7725600号.
01. 李文楷, 胡晓梅, 李佳豪, 2021. 基于一类数据的ROC/PR曲线模型评价系统. 软著登字第8446582号.
获奖情况
3. Methods in Ecology and Evolution期刊高引论文, WILEY (出版社), 2026.
2. Remote Sensing Specialty Group Student Honors Paper (2nd Place)，美国地理学家协会(AAG)，2013.
1. Talbert Abrams Award (2nd Honorable Mention)，美国摄影测量与遥感协会(ASPRS)，2013.
